Skip navigation
Noel Carboni 23,488 posts
Dec 23, 2006
Currently Being Moderated

12 core vs. 8 core for running Photoshop

Sep 19, 2012 3:18 PM

I had the Need for Speed, and boy have I been having some fun today.

 

I've just received my new (just off cutting-edge) Dell Precision T5500 workstation, and have moved all my drives over to it. This dual hex core 3.47 GHz Xeon X5690 system upgrades my previous dual quad core Dell Precision T5400 3.16 GHz Xeon X5460 setup.

 

The T5400 was no slouch, but benchmarks like Passmark showed the T5500 to be up to twice as powerful overall the T5400, so when I saw a price I liked I took the plunge.

 

  • The processors are faster: 3.47 GHz vs. 3.16 GHz
  • The processor design is one generation newer: Westmere vs. Harpertown
  • There are half again as many cores: 12 vs. 8
  • The T5500 has hyperthreading while the T5400 did not have it.
  • The T5500 uses DDR3 RAM instead of DDR2, giving about 1.5x the memory bandwidth (both systems run 1333 MHz ECC RAM).
  • Note that I have three times the RAM - 48 GB in the new system, vs. 16 GB in the T5400.

 

 

Unfortunately, the VisionTek ATI Radeon HD 7850 I had ordered along with it was defective out of the box, so for now I'm still using my prior 5670 card.  But without a video card upgrade, this gives me the unique opportunity to test just how Photoshop and other operations respond to the increased processing power as well as RAM, using the same disks, same software installation, same video card and drivers. So I set out to determine just how much this upgrade would affect the Photoshop work I do, which I'm sure will be interesting to folks here...

 

Here's what I have found:

 

A few things truly do take only half as long, though most are taking more like 2/3 as long and a few are surprisingly at about the same speed (probably implying my video card is the bottleneck). All times are T5500 vs. T5400:

 

  • Cold Photoshop CS6 x64 Startup Time - 3.2 seconds vs. 4.2.
  • Cold start Photoshop CS6 32 bit - 4.0 seconds vs. 5.6.

 

  • Second Photoshop CS6 x64 Startup Time (with most stuff cached) - 2.4 seconds vs. 3.4.
  • Warm start Photoshop CS6 32 bit - 2.6 seconds vs. 3.8.

 

  • Drag a 1.7GB multi-layer (compressed) PSB to Photoshop CS6 - 21.6 seconds vs. 34.8 seconds.
  • Save 1.7 GB compressed PSB - 19.8 seconds vs. 23.8 seconds.
  • Drag a layer of white dots around at 12.5% zoom -  5 frames per second, same speed as older system.
  • Drag a layer of black dots around at 12.5% zoom - 4 frames per second, same as older system.
  • Flatten the image:  13.8 seconds vs. 20.2.
  • Stroke a 1000 pixel soft brush diagonally across the 8000 x 8000 pixel image:  1.2 seconds vs. 1.6.
  • Drag a Canon 40D raw file with some development parameters already set and see the preview in Camera Raw:  2.6 seconds vs. 3.0.
  • Open that Raw file into Photoshop at 6144 x 4096 pixels, 16 bits/color:  6.2 seconds vs. 9.0.  I'm really going to feel this.
  • Fractal sharpen the image:  1 minute 41 seconds vs. 3 minutes 30 seconds (uses Perfect Resize 7, which multithreads well).
  • Open single color channel of a 10 megapixel astroimage through FITS Liberator:  4.6 seconds vs. 5.8
  • The http://clubofone.com/speedtest/ benchmark with Photoshop CS6: 12.8 seconds vs. 25.6 seconds.
  • The http://clubofone.com/speedtest/ benchmark with Photoshop CS5: 13.8 seconds vs. 26.2 seconds.
  • The http://clubofone.com/speedtest/ benchmark with Photoshop CS4: 15.4 seconds vs. 23.0 seconds.
  • Render the same 3D extrusion of the word Text (busied all 24 threads and got the fans really cranked up): 30 minutes 19 seconds vs. 45 mnutes 53 seconds.

 

 

T5400:

RenderTimeT5400.jpg

 

T5500 (this was a good stress test, the system sounded like it was ready to take off):

 

T5500 Test Render Time and Temperature.jpg

 

 

Interestingly, disk access to my already hyper-fast SSD array has actually increased a good bit, implying the disks and controller were capable of delivering and accepting data faster than the T5400 system itself.  As with many things listed above, the new system is about 1.5x to 2x faster on small operations.  For example, if I select all the entries in the root of drive C:, then choose Properties, the T5400 would enumerate all 511,000 files and stop counting up in about 32 seconds, at a rate of about 16,000 files / second.  The new system finishes that count in 20.4 seconds, at a rate of 25,000 files / second.  This means that my already very fast file access just feels snappier for everything.  My software builds now take only about 60% as long as they did before.

 

Looks like another week or more before I get my much faster video card, at which time I'll run through it all again.

 

I haven't tried stitching a panorama yet.  Right now as I write this it's doing the render I listed above.  The pano is next.  I think the big RAM is going to help a lot with that. 

 

Any other things you'd like me to try?  I won't be able to compare directly until I get the older system back together (been spending all my time playing with the new rig).

 

-Noel

 
Replies 1 2 Previous Next
  • Currently Being Moderated
    Sep 20, 2012 1:03 AM   in reply to Noel Carboni

    Not to curb your enthusiasm, but 30 minutes for some cheesy text? RLY? Adobe has still a long, long, long way to go before even coming close to any 3D program it would seem...

     

    Mylenium

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 20, 2012 8:04 AM   in reply to Noel Carboni

    Yeah, the panos are of interest! Try just building some reallllly big ones! I've just finished assembling, masking, adjusting and tiling out ortho images in the 15 - 30 GB ea. range using my single i7 quad core 5500 (SSD boot 10K data & scratch drives) with 24GB ram. Being an hourly employee made the wait times tolerable. I was system monitoring all along and have noticed very little cpu usage vs ram getting maxed out (and multiple 70GB temp files!). I kinda knew that when I spec'ed this box that I wanted more ram than cpu, but what you have now is what I want in a year. The 12 cores would come in very handy for large image processing in Lightroom too..

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 20, 2012 11:18 AM   in reply to Noel Carboni

    Noel

     

    Do you have Lightroom? I'd be real curious if someone with a box like this could see how long it would take to import and 1/1 thumbnail 100 or so 300MB image files at a crack (or ten and extrapolate the time). A pending job that will require the fastest possible visual analysis, correction and post processing of 1000s of this kind of aerial images seems to beg for the features available in LR but on my system its not very quick. I've heard the "PS likes ram and LR likes cpu's" so put 2+2 together and? Oh, and about GPU help?

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 20, 2012 2:23 PM   in reply to Noel Carboni

    That's OK - how about Bridge, any difference in performance there. re: thumb generation?

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 20, 2012 3:35 PM   in reply to Noel Carboni

    What OS?

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 21, 2012 8:48 AM   in reply to Noel Carboni

    "I'm not going to be moving to Windows 8 any time soon."

     

    You have inside knowledge?

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 21, 2012 9:00 AM   in reply to Noel Carboni

    Hmmm, I actually expected you to move on. When I ran the Win8 trial, it didn't take long for me to uninstall it. There seemed little to offer (I ran CS6 trial on it s well) and the sudden move by MS to junk the years of GUI design and interaction in favor of touch , for systems that didn't have touch as the process to manipulate movement between apps, did nothing to convince me to go there. In fact, it convinced me to abandon the trial. I uninstalled it and wiped the drive and put XP back (because of legacy HW for which no updated drivers were offered by Epson).

     

    But as a designer of apps for Windows, I rather would imagine you to, while finding some of Win 8 not to your liking, would nonetheless have to embrace it to continue offering apps.

     

    Maybe you are thinking of retiring?

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 21, 2012 12:07 PM   in reply to Noel Carboni

    No, not assume wrong, remember wrong! (sigh) I do recall now that you mentioned running Win8 on VM for development but alas! Memory fails me.

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 21, 2012 1:10 PM   in reply to Noel Carboni

    The flatten time: Is that for a 1.7G file? How many layers and what kind?

     

    Relatively speaking, my ol' slowpoke here opens PSCS6 hot in 5-6 sec, so I want to compare some real stuff!

     

    Another test I would love to do involves batch processing in DxO, but you don't have it.

     

    I don't suppose you would run the trial version and do a batch test, would you? My average batch runs approx 9 sec for only camera corrections. With OpenCL turned off, it's closer to 20 seconds.

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 22, 2012 12:04 AM   in reply to Noel Carboni

    Open 31.4 sec

    Save 37 sec

    Flatten 15.8 sec

     

    I saved the unflattened version after making a change in hue from 0 to1 so that I was actually saving an adjusted file.

     

    The Open took at first, 46 sec, Starting PS first then opening the file. Subsequent openings with PS running dropped to 31 sec. Flatten stayed very close as well as Save.

     

    Scratch generated 10G file

     

    Opening is comparable to your earlier machine, (the 31 sec reopen)  faster than your old  but overall obviously either work  station is faster, but not by a whole lot. Remember, I've using an Athlon IIx4, 2.88G cpu, 12G Ram, HDD drive. No hyperthreading.

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 22, 2012 11:21 AM   in reply to Noel Carboni

    I went back to run other tests especially the brush test. I was somewhat limited by my own stroke speed but when I mastered that, I was consistently under 1 sec (best time 0.8sec) on a flattened version and about 1 sec on the top layer (where I could see what I was doing).

     

    Open times varied but the most consistent was opening from Bridge. 45 sec. If I opened from Explorer there was a considerable lag time even showing PS and the timing was calculated from the moment PS showed up with the loader timing bar running.

     

    Finally My system is actually faster than your old one on flattening, by a fair amount! So I would be shooting myself in the foot opting for a work station running DDR2.

     

    My RAM setup is set at stock. I did run tests optimizing ram speed vs CL at Command Rate 1T and did see improvements but also instability. So I am at 1333MHz, CL9, 2T

     

    So everything is stock.

     

    Gives food for thought about any computer upgrades I was planning on giving this machine to my SO and building an Intel/Ivy Bridge for myself. The cost just for a processor and mobo will run several hundreds over an AMD Trinity/board combo, and Trinity is delivering pretty good performance for the PS filter, as a price point well below Intel (Amd's GPU on Trinity runs better than Intel)

     

    All that changes if I were to decide I want to learn and run Premier.

     

    I'm looking now to install a bigger C drive so I'll be looking at SSD's. Samsung seems to hold a strong edge.

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 23, 2012 7:23 AM   in reply to Noel Carboni

    Puget Systems just ran a test of video cards on a set of effects which employ the Mercury engine:

     

    http://www.pugetsystems.com/labs/articles/Adobe-Photoshop-CS6-GPU-Acce leration-161

     

    The 7750 and 7870 are FAPP tied (.75 sec difference )

     

    The upgrade 13.0.1 makes a significant increase in performance.

     

    I'll not be using the internal graphics of the Intel chip!

     

    -L

     

    Message was edited by: Hudechrome

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 23, 2012 8:35 AM   in reply to Noel Carboni

    I've been thinking about other, more decisive tests of your workstation vs conventionals. Premiere comes to mind, with a specific video to render.

     

    I'm also looking at new computer build using ECC memory. They seem to be found in workstation environments and the mobos over $200.

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 23, 2012 9:01 AM   in reply to Noel Carboni

    Actually, current research I did today on RAM indicate that the real difference between ECC and non versions is that ECC will detect and repair  an error and non ECC will detect and report but not repair.

     

    Perhaps this is an upgrade found within DDR3.

     

    I'm looking into this and will grab links as I do it.

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 23, 2012 11:34 AM   in reply to Noel Carboni

    non-ECC RAM can only detect major errors (whole chip, or fails at POST).

    ECC uses an extra bit to handle error detection and correction.

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 23, 2012 12:39 PM   in reply to Chris Cox

    What I said...or not?

     

    Oh, I said report, you didn't.

     

    Message was edited by: Hudechrome

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 23, 2012 12:40 PM   in reply to Hudechrome

    not -- non-ECC RAM will not detect most RAM errors, only the most blatent of problems.

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 23, 2012 12:48 PM   in reply to Chris Cox

    Thanks, Chris.

     

    Did you look at the test Puget Systems did on GPU acceleration and CS 13?

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 23, 2012 1:09 PM   in reply to Hudechrome

    I hadn't read it, but it sounds about right given the bug fixes made in 13.0.1.

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 23, 2012 2:08 PM   in reply to Chris Cox

    Here's snip of the averaged results:

     

    PSYS.JPG

    From here:

     

    http://www.pugetsystems.com/labs/articles/Adobe-Photoshop-CS6-GPU-Acce leration-161

     

    Message was edited by: Hudechrome

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 24, 2012 3:40 PM   in reply to Noel Carboni

    Did you check the website for the exact setup? (Silly question but I thought to ask anyway!)

     

    I'll run the tests once a get past  a networking problem between Win 7, XP and a new office "All-in-one" printer.

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 24, 2012 3:52 PM   in reply to Hudechrome

    I downloaded it and see there are two .atn's, one from each site. Which did you use, Noel, both?

     
    |
    Mark as:
  • Currently Being Moderated
    Sep 25, 2012 8:57 AM   in reply to Noel Carboni

    I'm confused. If I buy a cheap Quadro or Firepro in order to get 10 bit processing, would my performance with that card be slower than on a standard Nvidia GPU or not?

     
    |
    Mark as:
1 2 Previous Next

More Like This

  • Retrieving data ...

Bookmarked By (0)